Probability distributions

A quick understanding on how to use the torch distributions

torch.bernoulli()
torch.rand()
torch.poisson()
torch.normal()
torch.multinomial()

# Uncomment and run the appropriate command for your operating system, if required

# Linux / Binder
# !pip install numpy torch==1.7.0+cpu torchvision==0.8.1+cpu torchaudio==0.7.0 -f https://download.pytorch.org/whl/torch_stable.html

# Windows
# !pip install numpy torch==1.7.0+cpu torchvision==0.8.1+cpu torchaudio==0.7.0 -f https://download.pytorch.org/whl/torch_stable.html

# MacOS
# !pip install numpy torch torchvision torchaudio

import torch

Function 1 - torch.bernoulli

Draws binary random numbers (0 or 1) from a Bernoulli distribution.

# Example 1
a =  torch.distributions.Bernoulli(torch.tensor([0.41]))
a.sample()

tensor([0.])